Name: Tempreon
Author: Tempreon

LABSCO SUMMARY

The context travels; the model underneath can change.

Anything captured in one client is available in the next, which is the practical answer to re-explaining yourself every time you switch tools. Each account is isolated at the database level by row-level security, and the published AI Use Policy states the data is not used to train models.

What it is

A hosted MCP server that carries a knowledge layer about you — your Core Imprint, Knowledge Vault, Instincts and captured patterns — into every AI tool you connect. Where a company knowledge base brings company knowledge to AI, this is built around the individual operator, consultant or founder.

What you get

Core Imprint access — connected clients read your identity and adapt style to it
Knowledge search — query your stored knowledge base from any connected tool
Knowledge capture — tell the assistant to remember something and it is stored for later sessions
Task management — create, update and track tasks in conversation
File storage — save and retrieve documents across sessions
Network intelligence — query stored contact and relationship data
Learning — session patterns feed the Tempering system over time
Higher tiers add Agents (AI personalities), Chains (multi-step orchestration) and Decision Gates (behavioural rules)

Requirements

A Tempreon account, and about 15 minutes for the 13-dimension onboarding that seeds your Core Imprint. Connection is a single URL — https://api.tempreon.com/functions/v1/tempreon-mcp/mcp, and the /mcp suffix is the most common thing people leave off. Transport is Streamable HTTP, so there is no local config file and no process to manage. Authentication is OAuth 2.1 with PKCE and dynamic client registration per RFC 7591, so no pre-registration and no key to paste; protected-resource metadata is discoverable at /.well-known/oauth-protected-resource. Setup guides ship for Claude Desktop, Claude Code, Codex, ChatGPT and Cursor. Free and paid plans, paid from $19/month.

Setup effort

Follow the published steps

See installation options

USE CASES

01

Switching tools without re-explaining yourself

Connect a Bridge in each client and let the same layer answer in all of them.

02

Capturing a decision where you made it

Tell the assistant to remember it and find it in a different tool later.

03

Getting output that sounds like you

Let the connected client read your Core Imprint before it drafts.

BEFORE YOU INSTALL

What to know first

Requires

A Tempreon account (tempreon.com), authorized over OAuth in your browser — the first-time onboarding takes about 15 minutes

INSTALLATION

Connect your client

Server setup

Setup

Create your Tempreon account at tempreon.com and complete the 13-dimension onboarding to seed your Core Imprint (~15 minutes)

Generate a Bridge URL from your dashboard (Bridges section) — the endpoint is https://api.tempreon.com/functions/v1/tempreon-mcp/mcp and the /mcp suffix is required

Paste it into your MCP client: JSON-config clients use the mcpServers block; UI-driven clients (Claude Desktop, ChatGPT, Claude.ai web) paste the URL into the custom-connector dialog

Authorize via OAuth in the browser — log in, review the permissions, approve; the client stores the token and reconnects automatically

Hosted endpoint

ENDPOINT URL

https://api.tempreon.com/functions/v1/tempreon-mcp/mcp

Add this hosted endpoint to your MCP client, then sign in.

MCP Clients

Claude Code

CLAUDE CODE · JSON

{
  "mcpServers": {
    "tempreon": {
      "type": "http",
      "url": "https://api.tempreon.com/functions/v1/tempreon-mcp/mcp"
    }
  }
}

Any MCP client

ANY MCP CLIENT · JSON

{
  "mcpServers": {
    "tempreon": {
      "url": "https://api.tempreon.com/functions/v1/tempreon-mcp/mcp"
    }
  }
}

Claude Desktop, ChatGPT, Claude.ai

Paste the endpoint URL into the client's custom-connector setup dialog and authorize via OAuth

Tempreon